© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81078
    Prev
    Next
    INDEX
    Explanations

    `fileID:` or `name:` in code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on content‐bearing nouns and technical terms (e.g. “game,” “software,” “license,” “pyloric,” “narrowing,” “href”) rather than on function words or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vocal
    -0.81
     stop
    -0.72
     costitu
    -0.69
     cesse
    -0.69
     Stop
    -0.69
     Huck
    -0.67
    ickness
    -0.67
    балан
    -0.66
    obb
    -0.66
     subsid
    -0.66
    POSITIVE LOGITS
    Го
    0.80
    CMD
    0.75
     Ibn
    0.71
    CTRL
    0.70
    Info
    0.70
    До
    0.67
    На
    0.66
     melon
    0.66
    И
    0.65
    Поли
    0.65
    Activations Density 0.052%

    No Known Activations